pub fn shard_gdn_conv_rows(
src: DevicePtr,
dims: &TpGdnDims,
d_conv: usize,
gpu: &dyn GpuBackend,
) -> Result<(DevicePtr, usize, usize)>Expand description
Shard the depthwise conv1d BF16 weight [full_conv_dim, d_conv] to
[local_conv_dim, d_conv]. Channels ARE the QKV channels (one filter per
channel), so this uses the SAME [Q|K|V] segment pattern as the QKV
in-projection — the conv is NOT replicated across ranks.